Optical Flow Regularization of Implicit Neural Representations for Video Frame Interpolation
This addresses video frame interpolation for video processing applications, but it is incremental as it builds on existing implicit neural representation methods.
The paper tackled video frame interpolation by constraining implicit neural representation derivatives to satisfy optical flow constraints, achieving state-of-the-art results on limited motion ranges without extra training data.
Recent works have shown the ability of Implicit Neural Representations (INR) to carry meaningful representations of signal derivatives. In this work, we leverage this property to perform Video Frame Interpolation (VFI) by explicitly constraining the derivatives of the INR to satisfy the optical flow constraint equation. We achieve state of the art VFI on limited motion ranges using only a target video and its optical flow, without learning the interpolation operator from additional training data. We further show that constraining the INR derivatives not only allows to better interpolate intermediate frames but also improves the ability of narrow networks to fit the observed frames, which suggests potential applications to video compression and INR optimization.